Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    abbreviations or specific terms within a technological or scientific context

    oai_token-act-pair · gpt-3.5-turbo

    terms and concepts related to security and surveillance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itals
    -0.70
    sburg
    -0.68
     Franch
    -0.68
    rehens
    -0.67
    edin
    -0.67
    wer
    -0.63
     sexes
    -0.61
    illes
    -0.60
     Crimson
    -0.60
    ieth
    -0.59
    POSITIVE LOGITS
    Downloadha
    0.93
     whereby
    0.92
     aka
    0.86
    SPONSORED
    0.80
    meaning
    0.79
    which
    0.74
     privile
    0.71
    LOCK
    0.70
    formerly
    0.69
    mining
    0.69
    Act Density 0.570%

    No Known Activations